<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simon-etal-2019-unsupervised">
    <titleInfo>
        <title>Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Étienne</namePart>
        <namePart type="family">Simon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vincent</namePart>
        <namePart type="family">Guigue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Piwowarski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Unsupervised relation extraction aims at extracting relations between entities in text. Previous unsupervised approaches are either generative or discriminative. In a supervised setting, discriminative approaches, such as deep neural network classifiers, have demonstrated substantial improvement. However, these models are hard to train without supervision, and the currently proposed solutions are unstable. To overcome this limitation, we introduce a skewness loss which encourages the classifier to predict a relation with confidence given a sentence, and a distribution distance loss enforcing that all relations are predicted in average. These losses improve the performance of discriminative based models, and enable us to train deep neural networks satisfactorily, surpassing current state of the art on three different datasets.</abstract>
    <identifier type="citekey">simon-etal-2019-unsupervised</identifier>
    <identifier type="doi">10.18653/v1/P19-1133</identifier>
    <location>
        <url>https://aclanthology.org/P19-1133</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>1378</start>
            <end>1387</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses
%A Simon, Étienne
%A Guigue, Vincent
%A Piwowarski, Benjamin
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F simon-etal-2019-unsupervised
%X Unsupervised relation extraction aims at extracting relations between entities in text. Previous unsupervised approaches are either generative or discriminative. In a supervised setting, discriminative approaches, such as deep neural network classifiers, have demonstrated substantial improvement. However, these models are hard to train without supervision, and the currently proposed solutions are unstable. To overcome this limitation, we introduce a skewness loss which encourages the classifier to predict a relation with confidence given a sentence, and a distribution distance loss enforcing that all relations are predicted in average. These losses improve the performance of discriminative based models, and enable us to train deep neural networks satisfactorily, surpassing current state of the art on three different datasets.
%R 10.18653/v1/P19-1133
%U https://aclanthology.org/P19-1133
%U https://doi.org/10.18653/v1/P19-1133
%P 1378-1387

Markdown (Informal)

[Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses](https://aclanthology.org/P19-1133) (Simon et al., ACL 2019)

• Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses (Simon et al., ACL 2019)

ACL

• Étienne Simon, Vincent Guigue, and Benjamin Piwowarski. 2019. Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1378–1387, Florence, Italy. Association for Computational Linguistics.